use strict; # quote strings, declare variables
use warnings; # on by default
use warnings qw(FATAL utf8); # fatalize encoding glitches
- use open qw(:std :utf8); # undeclared streams in UTF-8
+ use open qw(:std :encoding(UTF-8)); # undeclared streams in UTF-8
use charnames qw(:full :short); # unneeded in v5.16
This I<does> make even Unix programmers C<binmode> your binary streams,
or open them with C<:raw>, but that's the only way to get at them
portably anyway.
-B<WARNING>: C<use autoload> and C<use open> do not get along with each other.
+B<WARNING>: C<use autodie> (pre 2.26) and C<use open> do not get along with each
+other.
=head2 ℞ 1: Generic Unicode-savvy filter
=head2 ℞ 2: Fine-tuning Unicode warnings
-As of v5.14, Perl distinguishes three sublasses of UTF‑8 warnings.
+As of v5.14, Perl distinguishes three subclasses of UTF‑8 warnings.
use v5.14; # subwarnings unavailable any earlier
no warnings "nonchar"; # the 66 forbidden non-characters
# cpan -i Unicode::Unihan
use Unicode::Unihan;
my $str = "東京";
- my $unhan = new Unicode::Unihan;
+ my $unhan = Unicode::Unihan->new;
for my $lang (qw(Mandarin Cantonese Korean JapaneseOn JapaneseKun)) {
printf "CJK $str in %-12s is ", $lang;
say $unhan->$lang($str);
# cpan -i Lingua::JA::Romanize::Japanese
use Lingua::JA::Romanize::Japanese;
- my $k2r = new Lingua::JA::Romanize::Japanese;
+ my $k2r = Lingua::JA::Romanize::Japanese->new;
my $str = "東京";
say "Japanese for $str is ", $k2r->chars($str);
or
$ export PERL_UNICODE=A
or
- use Encode qw(decode_utf8);
- @ARGV = map { decode_utf8($_, 1) } @ARGV;
+ use Encode qw(decode);
+ @ARGV = map { decode('UTF-8', $_, 1) } @ARGV;
=head2 ℞ 14: Decode program arguments as locale encoding
or
$ export PERL_UNICODE=S
or
- use open qw(:std :utf8);
+ use open qw(:std :encoding(UTF-8));
or
- binmode(STDIN, ":utf8");
+ binmode(STDIN, ":encoding(UTF-8)");
binmode(STDOUT, ":utf8");
binmode(STDERR, ":utf8");
=head2 ℞ 17: Make file I/O default to utf8
-Files opened without an encoding arugment will be in UTF-8:
+Files opened without an encoding argument will be in UTF-8:
$ perl -CD ...
or
$ export PERL_UNICODE=D
or
- use open qw(:utf8);
+ use open qw(:encoding(UTF-8));
=head2 ℞ 18: Make all I/O and args default to utf8
or
$ export PERL_UNICODE=SDA
or
- use open qw(:std :utf8);
- use Encode qw(decode_utf8);
- @ARGV = map { decode_utf8($_, 1) } @ARGV;
+ use open qw(:std :encoding(UTF-8));
+ use Encode qw(decode);
+ @ARGV = map { decode('UTF-8', $_, 1) } @ARGV;
=head2 ℞ 19: Open file with specific encoding
\p{Sk}, \p{Ps}, \p{Lt}
\p{alpha}, \p{upper}, \p{lower}
\p{Latin}, \p{Greek}
- \p{script=Latin}, \p{script=Greek}
+ \p{script_extensions=Latin}, \p{scx=Greek}
\p{East_Asian_Width=Wide}, \p{EA=W}
\p{Line_Break=Hyphen}, \p{LB=HY}
\p{Numeric_Value=4}, \p{NV=4}
use Unicode::UCD qw(num);
my $str = "got Ⅻ and ४५६७ and ⅞ and here";
my @nums = ();
- while (/$str =~ (\d+|\N)/g) { # not just ASCII!
+ while ($str =~ /(\d+|\N)/g) { # not just ASCII!
push @nums, num($1);
}
say "@nums"; # 12 4567 0.875
my @list = $col->sort(@old_list);
See the I<ucsort> program from the L<Unicode::Tussle> CPAN module
-for a conveninent command-line interface to this module.
+for a convenient command-line interface to this module.
=head2 ℞ 36: Case- I<and> accent-insensitive Unicode sort
use charnames qw(:full);
my $para = "This is a super\N{HYPHEN}long string. " x 20;
- my $fmt = new Unicode::LineBreak;
+ my $fmt = Unicode::LineBreak->new;
print $fmt->break($para), "\n";
=head2 ℞ 42: Unicode text in DBM hashes, the tedious way
# assume $uni_key holds a normal Perl string (abstract Unicode)
my $enc_key = encode("UTF-8", $uni_key, 1);
my $enc_value = $dbhash{$enc_key};
- my $uni_value = decode("UTF-8", $enc_key, 1);
+ my $uni_value = decode("UTF-8", $enc_value, 1);
=head2 ℞ 43: Unicode text in DBM hashes, the easy way
use strict;
use warnings;
use warnings qw(FATAL utf8); # fatalize encoding faults
- use open qw(:std :utf8); # undeclared streams in UTF-8
+ use open qw(:std :encoding(UTF-8)); # undeclared streams in UTF-8
use charnames qw(:full :short); # unneeded in v5.16
# std modules
"寿司" => 9.99, # sushi, Japanese
"おもち" => 2.65, # omochi, rice cakes, Japanese
"crème brûlée" => 2.00, # crema catalana
- "fideuà" => 4.20, # more noodles, Valencian (Catalan=fideuada)
+ "fideuà" => 4.20, # more noodles, Valencian
+ # (Catalan=fideuada)
"pâté" => 4.15, # gooseliver paste, French
"お好み焼き" => 8.00, # okonomiyaki, Japanese
);
# So the Asian stuff comes out in an order that someone
# who reads those scripts won't freak out over; the
# CJK stuff will be in JIS X 0208 order that way.
- my $coll = new Unicode::Collate::Locale locale => "ja";
+ my $coll = Unicode::Collate::Locale->new(locale => "ja");
for my $item ($coll->sort(keys %price)) {
print pad(entitle($item), $width, ".");
§4.2 Case, pages 120–122;
Case Mappings, page 166–172, especially Caseless Matching starting on page 170.
-=item
-
=item UAX #44: Unicode Character Database
=item UTS #18: Unicode Regular Expressions
for inclusion into your own programs without any encumbrance whatsoever.
Acknowledgement via code comment is polite but not required.
-=head1 REVISON HISTORY
+=head1 REVISION HISTORY
v1.0.0 – first public release, 2012-02-27
-
https://perl5.git.perl.org / perl5.git / blobdiff